Ishan Nigam

Papers

Total Citations

106

H-Index

About

Ishan Nigam is a leading researcher in computer vision and deep learning, with a primary focus on semantic segmentation and domain adaptation. His most influential work, "Ensemble Knowledge Transfer for Semantic Segmentation" (2018, 106 citations), tackles the critical challenge of domain shift—where models trained on one dataset fail when tested on another. Nigam pioneered ensemble-based knowledge transfer techniques that enable segmentation networks to generalize across different visual domains without requiring new labeled data. This contribution has proven essential for real-world applications like autonomous driving and medical imaging, where training and deployment conditions often differ. By leveraging multiple teacher models to guide a student network, his approach significantly improves robustness and accuracy under domain shifts. Nigam’s research bridges the gap between controlled training environments and unpredictable real-world scenarios, making deep learning models more practical and reliable. His work continues to inspire advances in domain generalization and transfer learning, cementing his reputation as an innovator in making computer vision systems adaptable and resilient across diverse visual contexts.